基于似然函数EM迭代的红外与可见光图像配准

聂宏宾; 侯晴宇; 赵明; 张伟

doi:10.3788/OPE.20111903.0657

您当前的位置：

首页 >

文章列表页 >

基于似然函数EM迭代的红外与可见光图像配准

信息科学 | 更新时间：2020-08-12

- 基于似然函数EM迭代的红外与可见光图像配准
- IR/visible image registration based on EM iteration of log-likelihood function
- 光学精密工程 2011年19卷第3期页码：657-663
- 作者机构：
  
  哈尔滨工业大学空间光学工程研究中心,黑龙江哈尔滨 150001
- 作者简介：
- 基金信息：
  
  基础科研资助项目(No.k1402060311)()
- DOI：10.3788/OPE.20111903.0657
  中图分类号： TP391
- 收稿日期：2010-09-25，
  
  修回日期：2010-12-31，
  
  网络出版日期：2011-03-22，
  
  纸质出版日期：2011-03-22
- 稿件说明：
移动端阅览
聂宏宾, 侯晴宇, 赵明, 张伟. 基于似然函数EM迭代的红外与可见光图像配准[J]. 光学精密工程, 2011,19(3): 657-663

NIE Hong-bin, HOU Qing-yu, ZHAO Ming, ZHANG Wei. IR/visible image registration based on EM iteration of log-likelihood function[J]. Editorial Office of Optics and Precision Engineering, 2011,19(3): 657-663
聂宏宾, 侯晴宇, 赵明, 张伟. 基于似然函数EM迭代的红外与可见光图像配准[J]. 光学精密工程, 2011,19(3): 657-663 DOI： 10.3788/OPE.20111903.0657.

NIE Hong-bin, HOU Qing-yu, ZHAO Ming, ZHANG Wei. IR/visible image registration based on EM iteration of log-likelihood function[J]. Editorial Office of Optics and Precision Engineering, 2011,19(3): 657-663 DOI： 10.3788/OPE.20111903.0657.

摘要

为了实现红外与可见光图像的自动配准

提出了基于似然函数EM迭代的图像配准算法。该算法以图像边缘作为配准点特征

将异源图像配准转化为边缘点集配准。通过点集的高斯混合建模建立了点集配准似然函数

以该函数作为目标函数

仿射变换参数作为优化变量

利用EM迭代优化方法进行最优变换参数求解。迭代过程中

引入基于概率密度自适应阈值分割的外点剔除机制

解决了外点对目标函数的干扰问题

实现了边缘点集的精确配准。利用实测的可见光和红外图像进行了算法验证

证明了该算法的有效性。

Abstract

In order to realize the automatic image registration for infrared images and visible images

an image registration method based on the Expectation Maximum(EM) iteration of the log-likelihood function is proposed. This method utilizes the image edge as the registration point

and thus the image registration is transferred into an edge point set registration. The point set is modeled as Gauss Mixture Model (GMM)

and the likelihood function of the point set registration is obtained. To solve the affine transform parameter

the likelihood function is maximized with EM iterations. And during the EM iterations

the probability density of edge point is segmented with an adaptive threshold to eliminate the outer points

and the interference of outer point with the likelihood function is overcome and the affine transform parameter is determined accurately. The experiments on image registration for infrared images and visible images are verified

and the results indicate that the proposed method is effective.

关键词

Keywords

references

KIM Y S, LEE J H, RA J B. Multi-sensor image registration based on intensity and edge orientation information[J]. Pattern Recognition,2008,41(11):3356-3365.[2] 王阿妮, 马彩文, 刘爽, 等. 基于角点的红外与可见光图像自动配准方法[J]. 光子学报, 2009,38(12):3328-3332. WANG A N, MA C W, LIU SH, et al.. Infrared-visual images automatic registration based on corners[J]. Acta Photonica Sinica, 2009,38(12):3328-3332. (in Chinese)[3] 冯宇平, 戴明, 孙立悦, 等. 图像自动拼接融合的优化设计[J]. 光学精密工程,2010,18(2):471-475. FENG Y P, DAI M, SUN L Y, et al.. Optimized design of automatic image mosaic[J]. Opt. Precision Eng., 2010,18(2):471-475. (in Chinese)[4] MIKOLAJCZYK K, SCHMID C. A performance evaluation of local descriptors[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(10):1615-1630.[5] 纪华, 吴元昊, 孙宏海, 等. 结合全局信息的SIFT特征匹配算法[J]. 光学精密工程,2009,17(2):339-444. JI H, WU Y H, SUN H H, et al.. SIFT feature matching algorithm with global information[J]. Opt. Precision Eng., 2009,17(2):339-444. (in Chinese)[6] BAY H, ESS A, TUYTELAARS T, et al.. Speeded-up robust features (Surf)[J]. Computer Vision and Image Understanding,2008,110(3):346-359.[7] 高峰, 文贡坚, 吕金建. 基于干线对的红外与可见光最优图像配准算法[J]. 计算机学报,2007,30(6):1014-1021. GAO F, WEN G J, LV J J. An optimal algorithm for IR/Visual image registration based on main-line-pairs[J]. Chinese Journal of Computers, 2007,30(6):1014-1021. (in Chinese)[8] COIRAS E, SANTAMARIA J, MIRAVET C. Segment-based registration technique for visual-infrared images[J]. Optical Engineering,2000,39(1):282-289.[9] BESL P J, MCKAY N.D. A method for registration of 3-D shapes[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1992,14(2):239-256.[10] LUO B, HANCOCK E R. A unified framework for alignment and correspondence[J]. Computer Vision and Image Understanding,2003,92(1):26-55.[11] ANDRIY M, XUBO S. Point set registration:coherent point drift[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(12):2262-2275.

浏览量

1006

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

目标运动轨迹匹配式的红外-可见光视频自动配准

基于目标增强与蝴蝶优化的红外与可见光图像融合

潜在低秩表示下的双判别器生成对抗网络的图像融合

改进的响尾蛇双模式细胞模型的图像融合

采用显著性分析与改进边缘方向直方图特征的红外与可见光图像配准